© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9180
    Prev
    Next
    INDEX
    Explanations

    a mixture of words related to importance/research and political/historical concepts.

    oai_token-act-pair · gemini-2.0-flash

    complex text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.61
    AndroidJUnit
    -0.52
     Phenomena
    -0.47
    thâu
    -0.47
    blas
    -0.47
    isait
    -0.46
    sort
    -0.46
    JScrollPane
    -0.46
     JScrollPane
    -0.46
     NSError
    -0.45
    POSITIVE LOGITS
    styleUrls
    0.63
     TestBed
    0.60
     pauvreté
    0.58
    vlád
    0.57
     actifs
    0.55
    EnableWeb
    0.53
     nôtre
    0.52
    ?>
    0.52
     dedans
    0.50
     tué
    0.50
    Activations Density 9.104%

    No Known Activations